Retrospective technology of segmentation and classification for GARCH models based on the concept of the $ \epsilon $-complexity of continuous functions

Alexandra Piryatinska; Boris Darkhovsky; Alexandra Piryatinska; Boris Darkhovsky

doi:10.3934/DSFE.2022012

Data Science in Finance and Economics

2022, Volume 2, Issue 3: 237-253. doi: 10.3934/DSFE.2022012

Previous Article Next Article

Research article

Retrospective technology of segmentation and classification for GARCH models based on the concept of the $ \epsilon $-complexity of continuous functions

Alexandra Piryatinska ^{1
,
,},
Boris Darkhovsky ²

1.
Department of Mathematics, San Francisco State University, 1600 Holloway ave, San Francisco, CA 94132, USA
2.
FRC CSC RAS

Received: 20 May 2022 Revised: 12 July 2022 Accepted: 18 July 2022 Published: 09 August 2022
JEL Codes: C14, C19, C22, C29

We consider a retrospective segmentation and classification problem for GARCH models. Segmentation is the partition of a long time series into homogeneous fragments. A fragment is homogeneous if only one mechanism generates it. The points of "concatenation" of homogeneous segments we call (by analogy with the term used in the stochastic literature) points of disorder or change-points. We call classification the separation of two relatively short time series generated by different mechanisms. By classification, we mean the way in which two groups of time series with unknown generating mechanism (in particularly, generated by GARCH models) can be distinguished, and the new time series can be assigned to the class. Our model free technology is based on our concept of $ \epsilon $-complexity of individual continuous functions. This technology does not use information about the time series generation mechanism. We demonstrate our approach on time series generated by GARCH models. We present simulations and real data analysis results confirming the effectiveness of the methodology.
- $ \epsilon $-complexity,
- GARCH models,
- model-free segmentation,
- classification
Citation: Alexandra Piryatinska, Boris Darkhovsky. Retrospective technology of segmentation and classification for GARCH models based on the concept of the $ \epsilon $-complexity of continuous functions[J]. Data Science in Finance and Economics, 2022, 2(3): 237-253. doi: 10.3934/DSFE.2022012

Related Papers:

Abstract

We consider a retrospective segmentation and classification problem for GARCH models. Segmentation is the partition of a long time series into homogeneous fragments. A fragment is homogeneous if only one mechanism generates it. The points of "concatenation" of homogeneous segments we call (by analogy with the term used in the stochastic literature) points of disorder or change-points. We call classification the separation of two relatively short time series generated by different mechanisms. By classification, we mean the way in which two groups of time series with unknown generating mechanism (in particularly, generated by GARCH models) can be distinguished, and the new time series can be assigned to the class. Our model free technology is based on our concept of $ \epsilon $-complexity of individual continuous functions. This technology does not use information about the time series generation mechanism. We demonstrate our approach on time series generated by GARCH models. We present simulations and real data analysis results confirming the effectiveness of the methodology.

References

[1]	Abanda A, Mori U, Lozano JA (2019) A review on distance based time series classification. Data Min Knowl Disc 33: 378-412. https://doi.org/10.1007/s10618-018-0596-4 doi: 10.1007/s10618-018-0596-4
[2]	Andreou E, Ghysels E (2009) Structural breaks in financial time series. Hand financ time ser 839-870. https://doi.org/10.1007/978-3-540-71297-8_37 doi: 10.1007/978-3-540-71297-8_37
[3]	Aue A, Horváth L (2013). Structural breaks in time series. J Time Ser Anal 34: 1–16. https://doi.org/10.1111/j.1467-9892.2012.00819.x doi: 10.1111/j.1467-9892.2012.00819.x
[4]	Bagnall A, Janacek G (2014) A run length transformation for discriminating between autoregressive time series. J Classif 31: 274–295. https://doi.org/10.1007/s00357-013-9135-6 doi: 10.1007/s00357-013-9135-6
[5]	Berkes I, Horváth L, Kokoszka P (2004) Testing for parameter constancy in GARCH (p, q) models. Stat probabil lett 70: 263–273. https://doi.org/10.1016/j.spl.2004.10.010 doi: 10.1016/j.spl.2004.10.010
[6]	Bollerslev T (1986) Generalized Autoregressive Conditional Heteroskedasticity. J Econometrics 31: 307–327. https://doi.org/10.1016/0304-4076(86)90063-1 doi: 10.1016/0304-4076(86)90063-1
[7]	Breiman L (2001) Random Forests. Mach Learn 45: 5–32. https://doi.org/10.1023/A:1010933404324 doi: 10.1023/A:1010933404324
[8]	Brodsky BS, Darkhovsky BE (1979) Identification of the change time in the random sequence.
[9]	Brodsky E, Darkhovsky B (2013) Nonparametric methods in change point problems. Springer Science Business Medi, New York.
[10]	Brooks C (2014) Introductory Econometrics for Finance (3rd ed.) Cambridge: Cambridge University Press.
[11]	Chao L, Zhipeng J, Yuanjie Z (2019) A novel reconstructed training-set SVM with roulette cooperative coevolution for financial time series classification. Expert Syst Appl 123: 283–298. https://doi.org/10.1016/j.eswa.2019.01.022 doi: 10.1016/j.eswa.2019.01.022
[12]	Chu C (1995) Detecting parameter shift in GARCH models. Economet Rev 14: 241–66. https://doi.org/10.1080/07474939508800318 doi: 10.1080/07474939508800318
[13]	Cortes C, Vapnik V (1995) Support-vector networks. Mach learn 20: 273-297. https://doi.org/10.1007/BF00994018 doi: 10.1007/BF00994018
[14]	Darkhovsky B (2020) On the complexity and dimension of continuous finite-dimensional maps. Theory of Probab Its Appl 65: 375–387. https://doi.org/10.1137/S0040585X97T990010 doi: 10.1137/S0040585X97T990010
[15]	Darkhovsky B, Piryatinska A (2014) New approach to the segmentation problem for time series of arbitrary nature. P Steklov I Math 287: 54–67. https://doi.org/10.1134/S0081543814080045 doi: 10.1134/S0081543814080045
[16]	Darkhovsky B, Piryatinska A, Kaplan A (2017) Binary classification of multichannel-eeg records based on the $\epsilon$-complexity of continuous vector functions. Comput meth prog bio 152: 131–139. https://doi.org/10.1016/j.cmpb.2017.09.001 doi: 10.1016/j.cmpb.2017.09.001
[17]	Darkhovsky B, Piryatinska A (2018) Model-free offline change-point detection in multidimensional time series of arbitrary nature via $\epsilon$-complexity: Simulations and applications. Appl Stoch Model Bus 34: 633–644. https://doi.org/10.1002/asmb.2303 doi: 10.1002/asmb.2303
[18]	Darkhovsky B, Piryatinska A (2019) Detection of Changes in Binary Sequences. In Workshop on Stochastic Models, Statistics and their Application 157–176. Springer, Cham. https://doi.org/10.1007/978-3-030-28665-1_12
[19]	Engle R (1982) Autoregressive Conditional Heteroskedasticity with Estimates of the Variance of United Kingdom Inflation. Econometrica 50: 987–1007. https://doi.org/10.2307/1912773. doi: 10.2307/1912773
[20]	Faouzi J (2022) Time Series Classification: A review of Algorithms and Implementations. Mach Learn https://hal.inria.fr/hal-03558165
[21]	Kokoszka P, Leipus R (2000) Change-point estimation in ARCH models. Bernoulli 6: 513–539. https://doi.org/10.2307/3318673 doi: 10.2307/3318673
[22]	Kolmogorov AN (1983) Combinatorial foundations of information theory and the calculus of probabilities. Russ math surv 38: 29–40.
[23]	Lamoureux CG, Lastrapes WD (1990) Persistence in variance, structural change, and the GARCH model. J Bus Econ Stat 8: 225–234. https://doi.org/10.1080/07350015.1990.10509794 doi: 10.1080/07350015.1990.10509794
[24]	Li Q, Wang L, Qiu F (2015) Detecting the structural breaks in GARCH models based on Bayesian method: The case of China share index rate of return. J Syst Sci Inf 3: 321–333. https://doi.org/10.1515/JSSI-2015-0321 doi: 10.1515/JSSI-2015-0321
[25]	Majumdar S, Laha AK (2020) Clustering and classification of time series using topological data analysis with applications to finance. Expert Syst Appl 162, 113868. https://doi.org/10.1016/j.eswa.2020.113868 doi: 10.1016/j.eswa.2020.113868
[26]	Smith D (2008) Testing for structural breaks in GARCH models. Appl Financ Econ 18: 845–862, https://doi.org/10.1080/09603100701262800. doi: 10.1080/09603100701262800
[27]	Song J, Kang J (2018) Parameter change tests for ARMA-GARCH models. Comput Stat Data Anal 121: 41–56. https://doi.org/10.1016/j.csda.2017.12.002 doi: 10.1016/j.csda.2017.12.002
[28]	Susto GA, Cenedese A, Terzi M (2018) Time-series classification methods: Review and applications to power systems data. Big data appl power syst 179–220. https://doi.org/10.1016/B978-0-12-811968-6.00009-7 doi: 10.1016/B978-0-12-811968-6.00009-7
[29]	Truong C, Oudre L, Vayatis N (2019) Greedy Kernel Change-Point Detection. IEEE T Signal Proces 67: 6204–6214. https://doi.org/10.1109/TSP.2019.2953670 doi: 10.1109/TSP.2019.2953670
[30]	Truong C, Oudre L, Vayatis N (2020) Selective review of offline change point detection methods. Signal Process 167: 107299. https://doi.org/10.1016/j.sigpro.2019.107299 doi: 10.1016/j.sigpro.2019.107299
[31]	Xing Z, Pe J, Keogh E (2010) A brief survey on sequence classification. ACM Sigkdd Explor Newsl 12: 40–48. https://doi.org/10.1145/1882471.1882478 doi: 10.1145/1882471.1882478

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)